用多智能体模拟旅行规划中的协商，提升共识达成效率。
MIND: Multi-agent inference for negotiation dialogue in travel planning
- 基于心智理论设计策略评估阶段，从语言推断对方意愿，准确率达90.2%
- 相比传统方法，高意愿命中率提升20.5%，辩论命中率提高30.7%
- 适合研究人机协商、个性化推荐系统的设计者参考
尽管多智能体辩论（MAD）研究已取得进展，但其在协调旅行规划等复杂利益相关方需求方面的效果仍不明确。为此，我们提出MIND（多智能体协商推理框架），旨在模拟具有异质偏好的旅行者之间真实的共识构建过程。基于心智理论（ToM），MIND引入策略评估阶段，通过语言细节推断对手意愿（w），准确率达90.2%。实验表明，MIND优于传统MAD框架，在高意愿命中率上提升20.5%，辩论命中率提高30.7%，有效优先处理高重要性约束。此外，基于LLM-as-a-Judge的定性评估显示，MIND在合理性（68.8%）和流畅性（72.4%）方面表现更优，整体胜率达68.3%。结果验证了MIND能有效建模人类协商动态，生成有说服力的共识。
原文摘要 · Abstract (English)
While Multi-Agent Debate (MAD) research has advanced, its efficacy in coordinating complex stakeholder interests such as travel planning remains largely unexplored. To bridge this gap, we propose MIND (Multi-agent Inference for Negotiation Dialogue), a framework designed to simulate realistic consensus-building among travelers with heterogeneous preferences. Grounded in the Theory of Mind (ToM), MIND introduces a Strategic Appraisal phase that infers opponent willingness (w) from linguistic nuances with 90.2% accuracy. Experimental results demonstrate that MIND outperforms traditional MAD frameworks, achieving a 20.5% improvement in High-w Hit and a 30.7% increase in Debate Hit-Rate, effectively prioritizing high-stakes constraints. Furthermore, qualitative evaluations via LLM-as-a-Judge confirm that MIND surpasses baselines in Rationality (68.8%) and Fluency (72.4%), securing an overall win rate of 68.3%. These findings validate that MIND effectively models human negotiation dynamics to derive persuasive consensus.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。